@inproceedings{xu-kim-2026-tokenization,
title = "Tokenization and Morphological Fidelity in {U}ralic {NLP}: A Cross-Lingual Evaluation",
author = "Xu, Nuo and
Kim, Ahrii",
editor = "Hettiarachchi, Hansi and
Ranasinghe, Tharindu and
Plum, Alistair and
Rayson, Paul and
Mitkov, Ruslan and
Gaber, Mohamed and
Premasiri, Damith and
Tan, Fiona Anting and
Uyangodage, Lasitha",
booktitle = "Proceedings of the Second Workshop on Language Models for Low-Resource Languages ({L}o{R}es{LM} 2026)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.loreslm-1.43/",
pages = "493--503",
ISBN = "979-8-89176-377-7",
abstract = "Subword tokenization critically affects Natural Language Processing (NLP) performance, yet its behavior in morphologically rich and low-resource language families remains under-explored. This study systematically compares three subword paradigms{---}Byte Pair Encoding (BPE), Overlap BPE (OBPE), and Unigram Language Model{---}across six Uralic languages with varying resource availability and typological diversity.Using part-of-speech (POS) tagging as a controlled downstream task, we show that OBPE consistently achieves stronger morphological alignment and higher tagging accuracy than conventional methods, particularly within the Latin-script group. These gains arise from reduced fragmentation in open-class categories and a better balance across the frequency spectrum. Transfer efficacy further depends on the downstream tagging architecture, interacting with both training volume and genealogical proximity.Taken together, these findings highlight that morphology-sensitive tokenization is not merely a preprocessing choice but a decisive factor in enabling effective cross-lingual transfer for agglutinative, low-resource languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-kim-2026-tokenization">
<titleInfo>
<title>Tokenization and Morphological Fidelity in Uralic NLP: A Cross-Lingual Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nuo</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahrii</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hansi</namePart>
<namePart type="family">Hettiarachchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alistair</namePart>
<namePart type="family">Plum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Gaber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damith</namePart>
<namePart type="family">Premasiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fiona</namePart>
<namePart type="given">Anting</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lasitha</namePart>
<namePart type="family">Uyangodage</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-377-7</identifier>
</relatedItem>
<abstract>Subword tokenization critically affects Natural Language Processing (NLP) performance, yet its behavior in morphologically rich and low-resource language families remains under-explored. This study systematically compares three subword paradigms—Byte Pair Encoding (BPE), Overlap BPE (OBPE), and Unigram Language Model—across six Uralic languages with varying resource availability and typological diversity.Using part-of-speech (POS) tagging as a controlled downstream task, we show that OBPE consistently achieves stronger morphological alignment and higher tagging accuracy than conventional methods, particularly within the Latin-script group. These gains arise from reduced fragmentation in open-class categories and a better balance across the frequency spectrum. Transfer efficacy further depends on the downstream tagging architecture, interacting with both training volume and genealogical proximity.Taken together, these findings highlight that morphology-sensitive tokenization is not merely a preprocessing choice but a decisive factor in enabling effective cross-lingual transfer for agglutinative, low-resource languages.</abstract>
<identifier type="citekey">xu-kim-2026-tokenization</identifier>
<location>
<url>https://aclanthology.org/2026.loreslm-1.43/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>493</start>
<end>503</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tokenization and Morphological Fidelity in Uralic NLP: A Cross-Lingual Evaluation
%A Xu, Nuo
%A Kim, Ahrii
%Y Hettiarachchi, Hansi
%Y Ranasinghe, Tharindu
%Y Plum, Alistair
%Y Rayson, Paul
%Y Mitkov, Ruslan
%Y Gaber, Mohamed
%Y Premasiri, Damith
%Y Tan, Fiona Anting
%Y Uyangodage, Lasitha
%S Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-377-7
%F xu-kim-2026-tokenization
%X Subword tokenization critically affects Natural Language Processing (NLP) performance, yet its behavior in morphologically rich and low-resource language families remains under-explored. This study systematically compares three subword paradigms—Byte Pair Encoding (BPE), Overlap BPE (OBPE), and Unigram Language Model—across six Uralic languages with varying resource availability and typological diversity.Using part-of-speech (POS) tagging as a controlled downstream task, we show that OBPE consistently achieves stronger morphological alignment and higher tagging accuracy than conventional methods, particularly within the Latin-script group. These gains arise from reduced fragmentation in open-class categories and a better balance across the frequency spectrum. Transfer efficacy further depends on the downstream tagging architecture, interacting with both training volume and genealogical proximity.Taken together, these findings highlight that morphology-sensitive tokenization is not merely a preprocessing choice but a decisive factor in enabling effective cross-lingual transfer for agglutinative, low-resource languages.
%U https://aclanthology.org/2026.loreslm-1.43/
%P 493-503
Markdown (Informal)
[Tokenization and Morphological Fidelity in Uralic NLP: A Cross-Lingual Evaluation](https://aclanthology.org/2026.loreslm-1.43/) (Xu & Kim, LoResLM 2026)
ACL